© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 50909
    Prev
    Next
    INDEX
    Explanations

    computational thinking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Alemania
    0.52
     either
    0.46
     privaten
    0.46
    */
    0.46
    hältnis
    0.45
     bulging
    0.45
    ii
    0.44
     directa
    0.44
     Eğer
    0.44
     mehrere
    0.43
    POSITIVE LOGITS
     EARL
    0.43
    䛛
    0.42
     εφαρ
    0.42
     CHARACTER
    0.41
    淑
    0.40
    თვის
    0.40
    ಎಸ್
    0.40
     இன்
    0.40
    Theory
    0.39
     CIRCU
    0.39
    Activations Density 0.000%

    No Known Activations